LL

llama 3.1 70B nemotron agent ja 120B i1

LlamaGGUF by mradermacherUpdated 2024-10-22
Download on Hugging Face
Parameters119B
Context128K
Layers137
Architecturellama
Smallest quant25.5 GB
Quick answer

llama 3.1 70B nemotron agent ja 120B i1 needs about 42.3 GB of memory at IQ2_S (a 37.2 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 9 quants, from 25.5 GB (IQ1_S) to 49.1 GB (IQ3_XS). Longer context needs more: at 32K tokens the KV cache alone adds about 18.4 GB.

llama 3.1 70B nemotron agent ja 120B i1 is a 119B-parameter Llama model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 9 quant files, from 25.5 GB (IQ1_S) to 49.1 GB (IQ3_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S25.5 GB 30.6 GB
Too big Get file →
IQ1_M27.9 GB 33.0 GB
Too big Get file →
IQ2_XXS31.9 GB 37.0 GB
Too big Get file →
IQ2_XS35.4 GB 40.5 GB
Too big Get file →
IQ2_S37.2 GB 42.3 GB
Too big Get file →
IQ2_M40.5 GB 45.6 GB
Too big Get file →
Q2_K44.2 GB 49.3 GB
Too big Get file →
IQ3_XXS46.1 GB 51.2 GB
Too big Get file →
IQ3_XS49.1 GB 54.2 GB
Too big Get file →

What GPU do you need for llama 3.1 70B nemotron agent ja 120B i1?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is IQ1_S (25.5 GB file, about 30.6 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ2_M (40.5 GB file, about 45.6 GB in use).

Which llama 3.1 70B nemotron agent ja 120B i1 quant should you choose?

IQ2_S (37.2 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

If memory is tight, the smallest file is IQ1_S at 25.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters119B
Layers137
Trained context131,072 tokens
KV cache (fp16)548 KB per token

Source

Quantized bymradermacher
FamilyLlama
Downloads (HF)170
Last updated2024-10-22

Frequently asked questions about llama 3.1 70B nemotron agent ja 120B i1

How much VRAM does llama 3.1 70B nemotron agent ja 120B i1 need?

About 42.3 GB at IQ2_S with an 8K context window. That is the 37.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run llama 3.1 70B nemotron agent ja 120B i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 30.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of llama 3.1 70B nemotron agent ja 120B i1 GGUF?

It depends on the quant: IQ1_S is 25.5 GB, IQ1_M is 27.9 GB, IQ2_XXS is 31.9 GB, IQ2_XS is 35.4 GB, IQ2_S is 37.2 GB, IQ2_M is 40.5 GB and 3 more.

What context length does llama 3.1 70B nemotron agent ja 120B i1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.6 GB at 8K and 18.4 GB at 32K.

Where can I download llama 3.1 70B nemotron agent ja 120B i1 GGUF?

The files are on Hugging Face in the mradermacher/llama-3.1-70B-nemotron-agent-ja-120B-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of llama-3.1-70B-nemotron-agent-ja-120B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other large models

All large models →